Suno, the popular AI music generator, is rolling out a beta speech feature that turns text into spoken audio, expanding from song creation into full synthetic voice generation and raising fresh questions about audio authenticity.
A new research paper proposes manifold-constrained initial noise optimization, a lightweight method to align diffusion-based generative models with human preferences and reward signals without costly fine-tuning.
A new arXiv paper argues that defining the null hypothesis is the hardest part of detecting memorization in generative models, proposing exact statistical tests to rigorously determine when a model is reproducing its training data.
A new DeBERTa-based detector tackles AI-generated text under adversarial paraphrasing and realistic deployment conditions, addressing a critical blind spot in synthetic media authentication.
New research reveals that fairness evaluations of adapted speech LLMs can swing dramatically based on a single random training seed — exposing a reproducibility blind spot that affects how we trust voice and audio AI systems.
New research shows how targeted rewriting can forge the stylistic fingerprints that identify which LLM wrote a text, undermining authorship attribution and raising fresh concerns for synthetic media detection.
Researchers have built an AI 'mind-reading' system that reconstructs the images a person is viewing using brain scan data, blending neural decoding with generative models in a striking new frontier for synthetic media.
AI video agents and video generation APIs solve different problems in synthetic media pipelines. Here's how they differ architecturally, when to use each, and what it means for building scalable AI video workflows.
New empirical research examines whether AI-generated social media posts can corrupt disaster social sensing systems — and whether current detection methods can tell synthetic crisis content from the real thing.
Under a new deal with the Trump administration, major tech leaders will self-regulate AI safety rather than face binding federal rules — a shift with major implications for how deepfakes and synthetic media get governed.
New research finds more than a third of freshly published webpages carry signs of AI generation, raising urgent questions about content authenticity, detection, and the future of a synthetic web.
Nvidia has unveiled a new AI safety platform designed to secure agentic AI systems following a wave of security breaches, adding runtime guardrails and content controls to protect enterprise deployments.